metadata

library_name: transformers
license: apache-2.0
base_model: cis-lmu/glot500-base
tags:
  - generated_from_trainer
datasets:
  - universal_dependencies
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: glot500_fintuned_en_ewt
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: universal_dependencies
          type: universal_dependencies
          config: en_ewt
          split: test
          args: en_ewt
        metrics:
          - name: Precision
            type: precision
            value: 0.9531084235094419
          - name: Recall
            type: recall
            value: 0.9548507779950685
          - name: F1
            type: f1
            value: 0.9539788051903922
          - name: Accuracy
            type: accuracy
            value: 0.9606748200873019

glot500_fintuned_en_ewt

This model is a fine-tuned version of cis-lmu/glot500-base on the universal_dependencies dataset. It achieves the following results on the evaluation set:

Loss: 0.1532
Precision: 0.9531
Recall: 0.9549
F1: 0.9540
Accuracy: 0.9607

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.0263	1.0	784	0.2097	0.9385	0.9394	0.9389	0.9477
0.1409	2.0	1568	0.1532	0.9531	0.9549	0.9540	0.9607

Framework versions

Transformers 4.46.3
Pytorch 2.5.1
Datasets 3.1.0
Tokenizers 0.20.3